Reference metadata describe statistical concepts and methodologies used for the collection and generation of data. They provide information on data quality and, since they are strongly content-oriented, assist users in interpreting the data. Reference metadata, unlike structural metadata, can be decoupled from the data.
Direzione centrale delle statistiche economiche (DCSE)
Servizio Statistiche strutturali sulle imprese, istituzioni pubbliche e non-profit (DCSE/SEC)
1.3. Contact name
Restricted from publication
1.4. Contact person function
Restricted from publication
1.5. Contact mail address
Via Tuscolana 1788, 00173 Roma
1.6. Contact email address
Restricted from publication
1.7. Contact phone number
Restricted from publication
1.8. Contact fax number
Restricted from publication
2.1. Metadata last certified
23 March 2022
2.2. Metadata last posted
23 March 2022
2.3. Metadata last update
23 March 2022
3.1. Data description
Structural business statistics (SBS) describes the structure, conduct and performance of economic activities, down to the most detailed activity level (several hundred economic sectors).
SBS covers all activities of the non-financial business economy with the exception of agricultural activities and personal services. Limited information is available on banking, insurance and pension funds.
Main characteristics (variables) of the SBS data category:
Business demographic variables (e.g. Number of enterprises)
"Output related" variables (e.g. Turnover, Value added)
"Input related" variables: labour input (e.g. Employment, Hours worked); goods and services input (e.g. Total of purchases); capital input (e.g. Material investments)
3.2. Classification system
Statistical Classification of Economic Activities in the European Community (NACE): NACE Rev.1 was used until 2001, NACE Rev. 1.1 since 2002, and NACE Rev 2 is used from 2008 onwards. Key data were double reported in NACE Rev.1.1 and NACE Rev.2 for 2008. From 2009 onwards, only NACE Rev.2 data are available.
The regional breakdown of the EU Member States is based on the Nomenclature of Territorial Units for Statistics (NUTS). Detailed information about the consecutive NUTS Regulations can be found at Eurostat's website
The SBS coverage was limited to Sections C to K of NACE Rev.1.1 until 2007. Starting from the reference year 2008 data is available for Sections B to N and Division S95 of NACE Rev.2. With 2013 as the first reference year information is published on Nace codes K6411, K6419 and K65 and its breakdown.
Enterprise - the definition is in line with the Regulation
3.6. Statistical population
All active (at least a part of the reference year) enterprises that are, according to their main activity, classified in sections B – J and L – N as well as in division 95 of section S.
Also it includes active enterprises classified in parts of section K (classes 6411 and 6419 as well as in division 65).
3.7. Reference area
The units active in Italy; the branches of foreign enterprises are included, while the activities abroad of the Italian units are excluded.
3.8. Coverage - Time
1996-2020
3.9. Base period
Not applicable.
Number of enterprises and number of local units are expressed in units.
Monetary data are expressed in millions of €.
Employment variables are expressed in units.
Per head values are expressed in thousands of € per head.
Ratios are expressed in percentages.
2020
The Italian SBS data reference year is the calendar year, and in most cases it corresponds to the fiscal year. For each enterprise with a different financial year than the calendar year, we decide to take into account the longest financial year, that is more than 6 months, in the corresponding SBS reference period. This decision is maintained every subsequent year for comparability reasons. Only in very few cases, when the fiscal year is more than 12 months, we estimate the 12 month calendar year.
6.1. Institutional Mandate - legal acts and other agreements
SBS Italian data are disseminated annually through the on-line database on the web site of Istat at the following address http://dati.istat.it/
10.4. Dissemination format - microdata access
Istat provides microdata files from its surveys free of charge for study and research purposes or for statistical-scientific purposes, in compliance with the regulations in force. The files released are those available at the time of the request and may be subject to statistical revisions and conficentiality rules (https://www.istat.it/en/analysis-and-products/microdata-files)
10.5. Dissemination format - other
Data are sent to Eurostat, either to be used in European aggregates or to be released also as national data.
10.6. Documentation on methodology
Rivista di statistica ufficiale n.1/2016 (http://www.istat.it/it/archivio/192775): The paper summarises the main features, methodological and technological details of the new statistical register on economic accounts of the Italian units. This documentation is only in English language.
Rivista di statistica ufficiale n.1-2-3/2017, 2nd issue (https://www.istat.it/it/archivio/253415, English: The paper describes the Regulations on data confidentiality, the methods applied to protect data, the IT aspects, and the channels used to disseminate the information. This documentation is only in English language.
The Information System on Quality (SIQual - accessible only from the intranet) contains metainformation on the statistical production processes (primary surveys, statistical compilations and informative systems) and secondary processes (pilot surveys, ad hoc modules, oversampling, quality control surveys or experiments) carried out by Istat. It includes metadata on process content, its operational characteristics (process phases and operations) and the quality considered both in terms of activities of prevention, monitoring and evaluation of errors (quality actions) and in terms of documentation on process and product quality with different degree of complexity (Methodological notes of the Statistical Yearbook, Quality declaration, Extensive documents on Quality). This documantation is only in Italian language.
10.7. Quality management - documentation
The quality report is transmitted to Eurostat, on an annual basis, when the compilation and validation of SBS data is completed.
Documentation is available on Eurostat website, quality reports are only available in English language
11.1. Quality assurance
Samples are extracted by reducing response burden on enterprises, administrative sources are used to reduce burden and recover non-responses.
11.2. Quality management - assessment
Italian SBS data are compiled with the use of administrative data covering basic statistical variables. A survey on enterprises is supplementarly conducted, in order to collect data for the statistical variables that cannot be retrived from administrative data. The use of administrative data is in terms of completeness, coverage of enterprises, and timeliness is very effective.
The data collection phase is continuously monitored. Sub phases of it are: 1) survey data collection monitoring, 2) survey data editing, 3) administrative data editing, 4) comparisons among different sources (administrative and survey), 5) estimation of missing data. In addition, the data are compared with the previous year's one and checked for large changes in the data, especially large deviations in the main variables.
The continuous cooperation of Istat with the tax and other administrative authorities providing data is basic.
The quality is assessed as high.
12.1. Relevance - User Needs
SBS data are used for the compilation of the Italian National Accounts.
The main national users of SBS data are researchers, economic analysts, students, enterprises, public authorities, politicians, scientists, economists, journalists.
At international level, SBS data are used by Eurostat.
12.2. Relevance - User Satisfaction
No survey related to the user's satisfaction is compiled.
12.3. Completeness
Structural Business Statistics cover the total set of variables defined by the relevant Regulations of the European Union.
13.1. Accuracy - overall
For the compilation of SBS data administrative sources are used, and a survey is used to collect data for variables non available in administrative sources, as admin data do not cover all the required statistical variables.
The accuracy and reliability of SBS data depends largely on the accuracy and completeness of the admin data. In general, it is difficult to evaluate their accuracy. The admin data checked for their completeness and relevance in terms of definitions of variables. When admin data are missing (3% of Italian enterprises) or incorrect, the imputation method is applied.
13.2. Sampling error
Starting from SBS2012, Istat have combined administrative sources with survey data aiming at reducing the sampling error and improving data quality.
SBS data have traditionally been transmitted by combining the estimates from the survey on small and medium enterprises with less than 100 persons employed (PMI) with those from the total survey on enterprises with 100 persons employed and more (SCI). Both surveys use administrative sources to integrate total non-responses.
The innovation in the production process involves the enterprises with less than 100 persons employed: variables estimates are based on exhaustive administrative sources for the main economic variables (turnover, purchases of goods and services, value added, personnel costs, etc.), combined with other economic variables not available from administrative sources, which are estimated exploiting PMI direct survey data by using either weighted regression estimators, or calibration (e.g. investments). The structural variables (number of persons employed, number of employees, economic activity, administrative region) come from the Business Register (Asia).
The administrative sources (Financial Statements of the corporate enterprises from Chambers of Commerce, Sector Studies survey and Tax Return data from the fiscal authority, and Social security data), have been analysed in terms of both coverage of the SBS target population as listed in the Business Register, and available variables. A comparative analysis of the variables observed in each administrative source and in the PMI survey has led to the integrated use of the relevant administrative sources according to a specific “hierarchy”. The sources’ hierarchy is based on how the variable definitions are close to the SBS ones and on the reliability of the sources (stability, availability, completeness, etc.).
Target variables not available in the administrative sources have been estimated through massive imputation, using a mixed approach, depending on the coverage rate of the target variables to be estimated: classical predictive model-based approaches have been used for estimating highly covered variables, while models based on PMI data have been adopted for estimating the remaining variables.
In this way a multidimensional micro data matrix has been built up (called “Frame”), containing the Business Register variables and the economic variables for all the SBS population units.
The activities carried out for building the Frame consist of: 1) analysis of available administrative sources (metadata analysis); 2) construction of the variables of interest; 3) comparison of variables at the micro level among the administrative sources and PMI survey data; 4) hierarchical selection of the sources; 5) analysis of the coverage of the business register; 6) estimation procedure with an approach based on a predictive model-based approach for the main variables (mass imputation) and a design-based approach for the other variables.
The main SBS variables are obtained from the Frame by sum (number of enterprises, number of persons employed, number of employees, turnover, personnel cost, value added at factor cost, etc) while others (such as investments) are estimated from the survey through calibration methodology.
From the reference year 2016 the sample survey PMI regards the enterprises with less than 250 persons employed while the total survey SCI regards the enterprises with 250 and more persons employed.
From the reference year 2017 the SBS Regulation No 295/2008 has been implemented with regards to the Statistical Unit Regulation (No. 696/93)
13.3. Non-sampling error
Some variables, such as the investments, are estimated by surveys while the other SBS ones are directly calculated from the micro database Frame built on the base of administrative sources.
For the variable "investments" which is estimated by survey by the calibration methodology, the bias resulting from non-response is limited. For the other variables of interest the bias is resulting by use of administrative sources.
The main source of errors is the non-responses and incomplete data provided by the enterprises.
As regards non-sampling errors, under-coverage or over-coverage, falsely classified units in the sample frame as well as unit or item non-response may occur.
Out-of-scope units are detected by including specific questions in the survey.
14.1. Timeliness
Data are transmitted to Eurostat 18 months after the reference year.
Data at national level are disseminated 23 months after the reference year.
14.2. Punctuality
Italian SBS series are currently sent to Eurostat on time.
15.1. Comparability - geographical
The same statistical concepts are applied in the entire national territory
15.2. Comparability - over time
1996-2007 in Nace Rev.1.1;
2008-2020 in Nace Rev.2
15.3. Coherence - cross domain
The coherence between number of enterprise and number of persons employed is checked between SBS and the Statistical Business Registers.
As for non-financial activities and the number of enterprises, both SBS and BD use the SBR as source. As for the number of persons employed and employees, SBS in very few cases uses information from surveys and BD information from the SBR. As for section K, the number of enterprise and the number of persons employed and employees for SBS comes from external sources, while BD uses the SBR.
15.4. Coherence - internal
The aggregates are always consistent with their main sub-aggregates.
Istat reduces the burden on the enterprises through the sample coordination methodology.
17.1. Data revision - policy
Annex I-IV: We make additional checks during data collection using administrative sources especially for the larger enterprises.
17.2. Data revision - practice
Data are corrected in case errors are detected.
18.1. Source data
Sample survey combined with administrative information.
Sample survey PMI for the enterprises with less than 250 persons employed: stratified design based on economic activity, size classes of persons employed and regions (76.514 units)
Total survey SCI for the enterprises with 250 and more persons employed (3.703 units)
The administrative source used in the process of data production are the following: Financial statement of the corporate enterprises from Chambers of Commerce; ISA (synthetic indices of reliability) data and Tax return data from the Fiscal authority; Social security data
Main economic variables (turnover, purchases of goods and services, personnel cost, value added, etc.) are directly available from the administrative sources. The number of enterprises, number of persons employed and number of employees are extracted from the Business Register.
The administrative sources are available at micro level and are used both as basic data and for imputation in case of non-response.
18.2. Frequency of data collection
Annual data collection
18.3. Data collection
The enterprises involved in the survey receive a communication via PEC (Certified Electronic Mail), containing an official letter by the Istat data collection department who invites to fill out an online questionnaire via the Business Portal (https://imprese.istat.it).
Many remainders are made.
18.4. Data validation
- Intra-dataset checks special for the administrative sources;
- Intra-source checks for choosing the best administrative source to use for the statistical purposes;
- Intra-dataset checks for the process of micro data validation using also the administraive sources;
- Intra-domain on the purpose to analyze some breaks;
In the process of data validation, the Integrative Notes of the Financial Statement, available from the Chambre of Commerce, are also used.
18.5. Data compilation
Data for non-respondent units are imputed using adminstrative sources (financial statements and tax data).
18.6. Adjustment
Not applicable
No further comments.
Structural business statistics (SBS) describes the structure, conduct and performance of economic activities, down to the most detailed activity level (several hundred economic sectors).
SBS covers all activities of the non-financial business economy with the exception of agricultural activities and personal services. Limited information is available on banking, insurance and pension funds.
Main characteristics (variables) of the SBS data category:
Business demographic variables (e.g. Number of enterprises)
"Output related" variables (e.g. Turnover, Value added)
"Input related" variables: labour input (e.g. Employment, Hours worked); goods and services input (e.g. Total of purchases); capital input (e.g. Material investments)
Enterprise - the definition is in line with the Regulation
All active (at least a part of the reference year) enterprises that are, according to their main activity, classified in sections B – J and L – N as well as in division 95 of section S.
Also it includes active enterprises classified in parts of section K (classes 6411 and 6419 as well as in division 65).
The units active in Italy; the branches of foreign enterprises are included, while the activities abroad of the Italian units are excluded.
2020
The Italian SBS data reference year is the calendar year, and in most cases it corresponds to the fiscal year. For each enterprise with a different financial year than the calendar year, we decide to take into account the longest financial year, that is more than 6 months, in the corresponding SBS reference period. This decision is maintained every subsequent year for comparability reasons. Only in very few cases, when the fiscal year is more than 12 months, we estimate the 12 month calendar year.
For the compilation of SBS data administrative sources are used, and a survey is used to collect data for variables non available in administrative sources, as admin data do not cover all the required statistical variables.
The accuracy and reliability of SBS data depends largely on the accuracy and completeness of the admin data. In general, it is difficult to evaluate their accuracy. The admin data checked for their completeness and relevance in terms of definitions of variables. When admin data are missing (3% of Italian enterprises) or incorrect, the imputation method is applied.
Number of enterprises and number of local units are expressed in units.
Monetary data are expressed in millions of €.
Employment variables are expressed in units.
Per head values are expressed in thousands of € per head.
Ratios are expressed in percentages.
Data for non-respondent units are imputed using adminstrative sources (financial statements and tax data).
Sample survey combined with administrative information.
Sample survey PMI for the enterprises with less than 250 persons employed: stratified design based on economic activity, size classes of persons employed and regions (76.514 units)
Total survey SCI for the enterprises with 250 and more persons employed (3.703 units)
The administrative source used in the process of data production are the following: Financial statement of the corporate enterprises from Chambers of Commerce; ISA (synthetic indices of reliability) data and Tax return data from the Fiscal authority; Social security data
Main economic variables (turnover, purchases of goods and services, personnel cost, value added, etc.) are directly available from the administrative sources. The number of enterprises, number of persons employed and number of employees are extracted from the Business Register.
The administrative sources are available at micro level and are used both as basic data and for imputation in case of non-response.
Annual
Data are transmitted to Eurostat 18 months after the reference year.
Data at national level are disseminated 23 months after the reference year.
The same statistical concepts are applied in the entire national territory
